Dataset Versions
Versions
640_3x
v14
· a year ago
best so far_640_3x_allmaped to trash
v13
· a year ago
best so far_640_3x
v12
· a year ago
classes in paper
v11
· a year ago
best_classes _from__test
v10
· a year ago
resize640-aug3x
v9
· a year ago
resize640-noAug
v7
· a year ago
all mapped to trash
v5
· a year ago
10 best classes
v4
· a year ago
10 classes
v3
· a year ago
added brightness
v2
· a year ago
Original
v1
· a year ago
v10
best_classes _from__test
Generated on Dec 29, 2023
3598 Total Images
View All ImagesDataset Split
Train Set 87%
3147Images
Valid Set 8%
299Images
Test Set 4%
152Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 42 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Rotation: Between -8° and +8°
Shear: ±3° Horizontal, ±3° Vertical
Grayscale: Apply to 5% of images
Hue: Between -15° and +15°
Saturation: Between -20% and +20%
Brightness: Between -20% and +20%
Exposure: Between -10% and +10%
Blur: Up to 0.75px
Cutout: 5 boxes with 2% size each